Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1740 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.1727. Min Act: -0.1700

Data Index: 228551 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1727. Min Range: -3.1727

Max Act: 3.1172. Min Act: -0.1700

Data Index: 1068571 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.9237. Min Act: -0.1700

Data Index: 1003535 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.9033. Min Act: -0.1700

Data Index: 1032055 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.9096. Min Act: -0.1700

Data Index: 578052 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8436. Min Act: -0.1700

Data Index: 822003 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8187. Min Act: -0.1700

Data Index: 740273 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8007. Min Act: -0.1700

Data Index: 894526 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8056. Min Act: -0.1700

Data Index: 1156949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.8008. Min Act: -0.1700

Data Index: 861980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7755. Min Act: -0.1700

Data Index: 806147 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7796. Min Act: -0.1700

Data Index: 1011471 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7995. Min Act: -0.1700

Data Index: 39087 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7550. Min Act: -0.1700

Data Index: 597595 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7647. Min Act: -0.1700

Data Index: 1038124 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7464. Min Act: -0.1700

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7408. Min Act: -0.1700

Data Index: 1275540 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7066. Min Act: -0.1700

Data Index: 740603 (C4 (Web Text))

Max Activating Token Index: 777

Text #18

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7182. Min Act: -0.1700

Data Index: 759685 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 3.1727. Min Range: -3.1727

Max Act: 2.7281. Min Act: -0.1700

Data Index: 785888 (C4 (Web Text))

Max Activating Token Index: 1023